Metadata-Version: 2.4
Name: reshimu-shor
Version: 0.1.0
Summary: Deterministic, non-LLM grounding & hallucination classifier for agent loops.
Project-URL: Homepage, https://github.com/reshimu/shor
Project-URL: Repository, https://github.com/reshimu/shor
Project-URL: Issues, https://github.com/reshimu/shor/issues
Author: Reshimu
License: MIT
Keywords: agents,ai-safety,classifier,grounding,hallucination,llm
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Software Development :: Libraries
Classifier: Typing :: Typed
Requires-Python: >=3.10
Provides-Extra: dev
Requires-Dist: mypy>=1.8; extra == 'dev'
Requires-Dist: pytest-cov>=4.0; extra == 'dev'
Requires-Dist: pytest>=8.0; extra == 'dev'
Requires-Dist: ruff>=0.2; extra == 'dev'
Description-Content-Type: text/markdown

# reshimu-shor

> Deterministic, non-LLM grounding & hallucination classifier for agent loops.

Python port of [@reshimu/shor](https://github.com/reshimu/shor). Functionally identical to the TypeScript implementation — same input produces the same classification. Sub-50ms. Zero runtime dependencies (stdlib only).

This is the minimal README. The full README ships at the project root in a later step.

## Install

```bash
pip install reshimu-shor
```

## Quick start

```python
from reshimu_shor import classify

result = classify(
    output="According to the report, Q3 revenue was $4.2M from 47 customers.",
    context="...the conversation history, tool outputs, documents the agent saw...",
)

print(result.level)            # 'GROUNDED' | 'PARTIAL' | 'UNGROUNDED' | 'INDETERMINATE'
print(result.score)            # [0, 1]
print(result.entities)         # per-entity lookup ledger
print(result.flag_for_review)  # True for PARTIAL and UNGROUNDED
```

## License

MIT
